2 papers
cs.CL2026
Forecasting Corpus-Sampling Disagreement in Masked Text Reconstruction
Hare Krishna
If a second text corpus were collected from the same population, how much would a predictor's outputs change? We study this question for masked-text reconstruction using a smoothed…
cs.LG2026
When Recursive Models Finish Computing
Hare Krishna, Shubham Singh, Stephen Ebert +1
Recursive models can continue updating their latent states beyond their nominal inference budget, so an incorrect output at that budget does not show whether computation is unfinis…